Generative artificial intelligence (AI)-based image generation using attribute-based slider controls

Attribute-based slider controls in GANs using text-to-image models and VQA enhance the precision and predictability of image generation, addressing the limitations of inconsistent variations in GANs.

EP4734065A1Pending Publication Date: 2026-04-29FUJITSU LTD
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
EP · EP
Patent Type
Applications
Current Assignee / Owner
FUJITSU LTD
Filing Date
2025-10-07
Publication Date
2026-04-29

Smart Images

  • Figure IMGAF001_ABST
    Figure IMGAF001_ABST
Patent Text Reader

Abstract

In an embodiment, generative Al-based image generation using attribute-based slider control is provided. A prompt indicative of a description of a first image is received. The first image is generated based on the prompt, by a text-to-image model. A set of attributes associated with the description is determined, based on a first language model. The set of attributes corresponds to semantics associated with the first image. Based on a second language model, a set of questions associated with prompt is generated. Slider boundary values and initial slider value are generated, based on the set of questions and the first image. A set of sliders is generated based on the slider boundary values and the initial slider value. Each slider corresponds to an attribute. A user input associated with the set of sliders is received and a second image is generated. The second image is rendered.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Method and apparatus for automated content database creation and real-time, adaptive tutoring and grading

    US20240274025A1

  • Neural compositing by embedding generative technologies into non-destructive document editing workflows

    US20240135611A1